colsample_btree=1, # 所有特征建立决策树
scale_pos_weight=1, # 解决样本个数不平衡的问题
random_state=27, # 随机数
slient=0,
)
xg.fit(feature_train_balance, label_train_balance)
xg_pred = xg.predict_proba(feature_test_balance)[:, 1]
xg_evaluation = valid.evaluate(
label_test_balance, xg_pred, save_path="../data/xg_evaluation.json"
)
plot_evaluation(label_test_balance, xg_pred, "../figure", method="XG")
#%%
lb = LogitBoost(n_estimators=200, random_state=0) # base_estimator=LogisticRegression()
lb.fit(feature_train_balance, label_train_balance)
lb_pred = lb.predict_proba(feature_test_balance)[:, 1]
lb_evaluation = evaluate(
label_test_balance, lb_pred, save_path="../data/lb_evaluation.json"
)
plot_evaluation(label_test_balance, lb_pred, "../figure", method="LB")
#%%
from feature import valid
#%%
# Auto-tunan_column_listne model for pandemic
# 1. XGboost
# 2. XGboost - additive learning
# 3. LogisticBoosting - additive learning
# 4. dummy Logistic
# 5. Transfer Logistic
from preprocess import transform
def _toy_dataset_test(load_func,
test_size=(1. / 3),
random_state=0,
min_score_train=0.9,
min_score_test=0.9):
"""Create a classification unit test from a scikit-learn toy dataset."""
# Fetch the dataset
data = load_func()
X = data.data
y = data.target_names[data.target]
# Distinct classes
classes = data.target_names
n_classes = len(classes)
# Binary/multiclass classification indicator
is_binary = (n_classes == 2)
# Shuffle data and split it into training/testing samples
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=test_size, shuffle=True, stratify=y,
random_state=random_state)
for bootstrap in (True, False):
# Fit a LogitBoost model
logitboost = LogitBoost(bootstrap=bootstrap, random_state=random_state)
logitboost.fit(X_train, y_train)
# Compute accuracy scores and assert minimum accuracy
score_train = logitboost.score(X_train, y_train)
score_test = logitboost.score(X_test, y_test)
assert score_train >= min_score_train, \
("Failed with bootstrap=%s: training score %.3f less than %.3f"
% (bootstrap, score_train, min_score_train))
assert score_test >= min_score_test, \
("Failed with bootstrap=%s: testing score %.3f less than %.3f"
% (bootstrap, score_test, min_score_test))
# Get probabilities and the decision function
predict_proba = logitboost.predict_proba(X_test)
decision_function = logitboost.decision_function(X_test)
# predict_proba() should always return (n_samples, n_classes)
assert predict_proba.shape == (X_test.shape[0], n_classes)
# decision_function() shape depends on the classification task
if is_binary:
assert decision_function.shape == (X_test.shape[0], )
else:
assert decision_function.shape == (X_test.shape[0], n_classes)
# Check that the last item of a staged method is the same as a regular
# method
staged_predict = np.asarray(list(logitboost.staged_predict(X_test)))
staged_predict_proba = \
np.asarray(list(logitboost.staged_predict_proba(X_test)))
staged_decision_function = \
np.asarray(list(logitboost.staged_decision_function(X_test)))
staged_score = \
np.asarray(list(logitboost.staged_score(X_test, y_test)))
np.testing.assert_equal(staged_predict[-1], logitboost.predict(X_test))
np.testing.assert_almost_equal(staged_predict_proba[-1],
logitboost.predict_proba(X_test))
np.testing.assert_almost_equal(staged_decision_function[-1],
logitboost.decision_function(X_test))
np.testing.assert_almost_equal(staged_score[-1],
logitboost.score(X_test, y_test))
# contributions() should return one non-negative number for each
# estimator in the ensemble
contrib = logitboost.contributions(X_train)
assert contrib.shape == (logitboost.n_estimators, )
assert np.all(contrib >= 0)
def model_comp(X_train, X_test, y_train, y_test, title=""):
xgboost_model = XGBClassifier(learning_rate=0.01,
max_depth=3,
n_estimators=700,
random_state=8)
gradient_boost_model = GradientBoostingClassifier(learning_rate=0.01,
max_depth=4,
max_features='log2',
min_samples_leaf=4,
n_estimators=280,
subsample=0.25,
random_state=8)
random_forest_model = RandomForestClassifier(n_estimators=300,
max_depth=3,
verbose=1,
random_state=8)
svm_model = SVC(kernel='poly', probability=True, verbose=1, random_state=8)
knn_model = KNeighborsClassifier(n_neighbors=3)
elm_model = MLPClassifier(hidden_layer_sizes=(80, ),
activation='logistic',
learning_rate_init=0.01,
verbose=1)
adaboost_model = AdaBoostClassifier(n_estimators=300,
learning_rate=0.01,
random_state=8)
logitboost_model = LogitBoost(n_estimators=300,
learning_rate=0.01,
random_state=8)
xgboost_model.fit(X_train, y_train)
gradient_boost_model.fit(X_train, y_train)
random_forest_model.fit(X_train, y_train)
svm_model.fit(X_train, y_train)
knn_model.fit(X_train, y_train)
elm_model.fit(X_train, y_train)
adaboost_model.fit(X_train, y_train)
logitboost_model.fit(X_train, y_train)
p_random_forest = random_forest_model.predict_proba(X_test)
p_gradient_boost = gradient_boost_model.predict_proba(X_test)
p_xgboost = xgboost_model.predict_proba(X_test)
p_svm = svm_model.predict_proba(X_test)
p_knn = knn_model.predict_proba(X_test)
p_elm = elm_model.predict_proba(X_test)
p_adaboost = adaboost_model.predict_proba(X_test)
p_logitboost = logitboost_model.predict_proba(X_test)
random_forest_ll = log_loss(y_test, p_random_forest)
gradient_boost_ll = log_loss(y_test, p_gradient_boost)
xgboost_ll = log_loss(y_test, p_xgboost)
svm_ll = log_loss(y_test, p_svm)
knn_ll = log_loss(y_test, p_knn)
elm_ll = log_loss(y_test, p_elm)
adaboost_ll = log_loss(y_test, p_adaboost)
logitboost_ll = log_loss(y_test, p_logitboost)
strng0 = "\n" + title
strtest = "\nLength of test data: " + str(len(y_test))
strng2 = "\n------------------"
strng4 = "\nGradient Boost Log Loss " + str(gradient_boost_ll)
strng5 = "\nRandom Forest Log Loss " + str(random_forest_ll)
strng6 = "\nXGBoost Log Loss " + str(xgboost_ll)
strng7 = "\n------------------"
strng9 = "\nSVM Log Loss " + str(svm_ll)
strng10 = "\nKNN Log Loss " + str(knn_ll)
strng11 = "\nELM Log Loss " + str(elm_ll)
strng12 = "\nAdaBoost Log Loss " + str(adaboost_ll)
strng13 = "\nLogitBoost Log Loss " + str(logitboost_ll)
prntstr = strng0 + strtest + strng2 + strng4 + strng5 + strng6 + strng7 + strng9 + strng10 + strng11 + strng12 + strng13
print(prntstr)
write_to_file(prntstr)
return xgboost_model, random_forest_model, adaboost_model
